Credit selection in collateralized loan obligation: Efficient approximation through linearization and clustering
Bibliographic record
Abstract
• CLOs help channel funds to SMEs and strengthen real-economy financing • Securitization lowers SME funding costs for financial institutions • Loan selection is an NP-hard mixed-integer nonlinear optimization task • Large pool approximation, linearization, and clustering improve efficiency • Method outperforms derivative-free algorithms in speed and solution quality Despite its role in the global financial crisis, collateralized loan obligation (CLO) remains a powerful tool to direct funds towards the real economy. In particular, it enables development banks to increase credit supply to small and medium-sized enterprises (SMEs). Public financial institutions thus face the challenge of identifying a subset of credits to be pooled in a CLO for the sake of reaching a specific financial target. The resulting problem is a mixed-integer nonlinear program, (MINLP), which is NP-hard. In this paper, we propose an approximate optimization problem that combines a large pool (LP) approximation, linearization of ancillary variables, and clustering. This approximate optimization problem delivers a solution (i) that improves the value of the objective function under the exact criterion compared to the solution of a derivative-free mixed-integer algorithm solving the exact problem and (ii) in a much lower computation time. As illustration, we consider two realistic CLO objective functions. We rely on the celebrated one-factor Gaussian copula in the main examples, but make clear that this assumption is not a restriction and can be relaxed. Our results contribute to reduce the funding cost of SMEs and are of direct interest for securitization stakeholders such as public financial institutions, commercial banks and pension funds.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.013 | 0.003 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".